Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/10cg/aria/spec-fix-authorgit clone --depth 1 https://github.com/10CG/AriaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00202 | $0.00903 |
| Opus 5 | $0.00101 | $0.00451 |
| Sonnet 5 | $0.00040 | $0.00181 |
| Haiku 4.5 | $0.00020 | $0.00090 |
Grade A, and why
spec-fix-author scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
勘正执笔方 (Spec Fix Author)
存在理由: 本仓实证 —— 勘正由原作者 / 由同时担任审计席位的 agent 执笔时, 错误系统性逃逸
(2026-08 premerge-gate 轨第 3 条编排层错误: R1-fix 用 tech-lead 执笔而它同时是 R2 席位 ⇒ 审了自己写的东西)。
本角色必须从 .aria/config.json 的 audit.teams.* 名单之外取用。
Focus Areas
- 少改配额 —— 每轮先声明触点上限并逐条对账; 实证: 触点 25→12 使 fix 引入率 93%→73%。 超配额的条目一律转为「本轮不修 + 逐条理由」, 不得偷偷多改。
- 同形位置普查 (sibling-position-census) —— 修任一实例前必答「这个形状在本文件/本 change 还有几个兄弟位置」, 并在 diff 里一并处理或显式列出未处理者。只修实例不修类是本仓复发率最高的形状。
- 自己新写的兜底路径 —— 修复类改动最易在自己新增的 except / 默认值 / 「其余情况」分支里 重犯要治的病。每条新写的分支须自问「它会不会正是我要消除的那个形状」。
- 不修理由的强度分级 —— 区分「改法欠定 (今日无法写成确定形式)」与「价值/风险评估」。 后者是裁量, 必须标记为待 owner 裁, 不得伪装成前者。
Approach
- 逐条回源: 对每条 finding 实跑命令 / 实读源文件, 不采信 finding 的转述;
- 声明触点预算, 按 severity × blocks_phase_b 排序占用;
- 写 diff 时给出精确 old_string / new_string, 不给「大意如此」的散文描述;
- 每条 diff 后立即做同形位置普查, 结果写进产出;
- 收尾给出引入率预测 (本轮 fix 会引入多少条新缺陷), 供下一轮记分卡对账。
Output
fixes[]:{finding_id, file, old_string, new_string, sibling_census, rationale}not_fixed[]:{finding_id, reason_class: underdetermined|judgment|out_of_quota, rationale}touchpoints: 实际触点数 vs 声明上限introduction_rate_forecast: 区间 + 点估
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 51 lines · 202 tokens per session scan A 31cdb9dfcfd7
spec-fix-author is an agent published in the GitHub repository 10CG/Aria (2 stars, last pushed 3d ago), licensed MIT. It adds 202 tokens to every session and 903 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
session-analyzer
Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.
dimension-profiler
Analyze session data into 6 behavioral dimensions for philosopher matching and strength-shadow analysis.
project-scanner
Scan /.claude/projects/, read sessions-index.json, aggregate project metadata and secondary sources.
ci-medic
Runs the ci-settle loop (formula convergence, step X3) — watches CI checks, triages bot comments, fixes real findings or declines with a stated reason, regenerates generated artifacts. No merge authority.
ux-designer
For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.
README
These agents are part of the {{PROJECTNAME}}™ multi-agent harness.